INDEX

Explanations

variations of the root "ribose" in different contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagext

-0.77

QMetaType

-0.61

umenical

-0.61

Tikang

-0.60

 désolés

-0.60

ьаж

-0.60

్రామ

-0.59

elernt

-0.59

)))));

-0.59

hede

-0.59

POSITIVE LOGITS

ri

2.72

ri

2.53

Ri

2.41

Ri

2.30

RI

2.05

RI

1.88

 Ripper

1.38

Rie

1.35

Rig

1.31

Rig

1.29

Activations Density 0.179%

variations of the root "ribose" in different contexts

No Comments

No Known Activations